great0001 commited on
Commit
3eec1fb
·
verified ·
1 Parent(s): f02a84c

Training in progress, step 9, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cd51b22b04a464b3b96e6835342fbd297f5b0cb5f713a136305e3244e977c7c9
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20f9a577829274f33fb0b4159c801f96e909840eb53a7b643f282b0baa25a0b0
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ffb486e3674f872618175db0c343df52ef25efa49294ff78a8f1b6c9b89feea
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48cd32a9dc344834906521265bdd0253f3aa5ea294f2f4aa21daf92a32a80b67
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7b14d0c915e2c4063f110f3dbec036a026b529b8820509b2913f154771be18b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9ed9626ba6e412f40126198b85320c11d70caab3bee87c19069e3aea6dd4f83
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.0012719949120203519,
5
  "eval_steps": 3,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 14.556,
74
  "eval_steps_per_second": 7.282,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 2103203743137792.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0019079923680305278,
5
  "eval_steps": 3,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 14.556,
74
  "eval_steps_per_second": 7.282,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.001483994064023744,
79
+ "grad_norm": 3.342315673828125,
80
+ "learning_rate": 0.00014,
81
+ "loss": 5.2492,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0016959932160271359,
86
+ "grad_norm": 4.831226348876953,
87
+ "learning_rate": 0.00016,
88
+ "loss": 4.1735,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0019079923680305278,
93
+ "grad_norm": 3.755944013595581,
94
+ "learning_rate": 0.00018,
95
+ "loss": 5.7689,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0019079923680305278,
100
+ "eval_loss": 1.2824764251708984,
101
+ "eval_runtime": 136.4582,
102
+ "eval_samples_per_second": 14.561,
103
+ "eval_steps_per_second": 7.284,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 3154805614706688.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null